| .. |
|
_v2
|
feat(cache): select Rust caching through explicit cache objects (#43601)
|
2026-09-29 00:01:44 +00:00 |
|
a2a_protocol
|
refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)
|
2026-10-15 21:08:47 +00:00 |
|
anthropic_interface
|
refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)
|
2026-10-15 21:08:47 +00:00 |
|
assistants
|
feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)
|
2026-11-10 17:08:29 +00:00 |
|
batch_completion
|
|
|
|
batches
|
feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)
|
2026-11-10 17:08:29 +00:00 |
|
caching
|
fix(caching): key cached async clients by a per-loop token instead of id(loop) (#48877)
|
2026-11-05 01:39:40 +00:00 |
|
chat_completions
|
refactor(python-bridge): ship a signature base and read the resolved call (#45450)
|
2026-10-08 17:20:29 -07:00 |
|
completion_extras
|
fix(anthropic): keep every non-streamed reasoning item for Messages clients on the line's bridge
|
2026-11-07 06:06:59 -08:00 |
|
compression
|
refactor(llms): expose public names for private provider helpers (#45037)
|
2026-10-07 08:49:25 -07:00 |
|
containers
|
feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)
|
2026-11-10 17:08:29 +00:00 |
|
decisions
|
feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)
|
2026-11-10 17:08:29 +00:00 |
|
embeddings
|
refactor(python-bridge): ship a signature base and read the resolved call (#45450)
|
2026-10-08 17:20:29 -07:00 |
|
endpoints/speech/speech_to_completion_bridge
|
|
|
|
evals
|
|
|
|
experimental_mcp_client
|
fix(mcp): backport #47034 to lts/1.108.x
|
2026-11-06 17:08:23 -08:00 |
|
files
|
feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)
|
2026-11-10 17:08:29 +00:00 |
|
fine_tuning
|
feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)
|
2026-11-10 17:08:29 +00:00 |
|
google_genai
|
refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)
|
2026-10-15 21:08:47 +00:00 |
|
harness
|
refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)
|
2026-10-15 21:08:47 +00:00 |
|
images
|
feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)
|
2026-11-10 17:08:29 +00:00 |
|
integrations
|
fix(guardrails): check a model-level post_call response once across the proxy and deployment layers (#50300)
|
2026-11-07 07:45:04 +09:00 |
|
interactions
|
refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)
|
2026-10-15 21:08:47 +00:00 |
|
litellm_core_utils
|
fix(transcription): read the frame count once to keep the type gate flat
|
2026-11-10 06:43:07 +00:00 |
|
llms
|
feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)
|
2026-11-10 17:08:29 +00:00 |
|
messages
|
feat(anthropic): generate auto mode safeguard_results with a classifier model on the /v1/messages chat bridge (#45600)
|
2026-10-14 13:09:11 +00:00 |
|
models
|
fix(proxy): allow model instances in LiteLLM_EndUserTable validation (#41677)
|
2026-10-15 10:57:26 -07:00 |
|
ocr
|
refactor(python-bridge): ship a signature base and read the resolved call (#45450)
|
2026-10-08 17:20:29 -07:00 |
|
passthrough
|
fix(bedrock)!: backport #47429 deployment guardrailConfig on /bedrock pass-through routes to lts/1.108.x
|
2026-11-07 16:45:18 -08:00 |
|
proxy
|
Merge pull request #50962 from BerriAI/litellm_backport_39966_lts_1_108_x
|
2026-11-10 10:24:14 -08:00 |
|
proxy_auth
|
refactor(types): replace Any with real types across 29 more backend files
|
2026-09-08 10:14:07 +00:00 |
|
rag
|
refactor(types): replace Any with proven types in 24 files (#46663)
|
2026-10-15 06:10:12 -07:00 |
|
realtime_api
|
feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)
|
2026-11-10 17:08:29 +00:00 |
|
repositories
|
fix(proxy): reset end-user spend in committed pages so the budget cascade survives a large LiteLLM_EndUserTable (#46502)
|
2026-10-15 19:47:12 -07:00 |
|
rerank_api
|
refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)
|
2026-10-15 21:08:47 +00:00 |
|
responses
|
Merge pull request #50456 from BerriAI/litellm_backport_49076_lts_1_108_x
|
2026-11-09 19:36:36 +00:00 |
|
router_strategy
|
fix(router): preserve tag fail-open policy through affinity and cooldown (#48470)
|
2026-11-05 14:56:28 -08:00 |
|
router_utils
|
fix(videos)!: keep model_id in proxy video ids so per-model keys resolve on status/content (#44614)
|
2026-11-09 15:05:22 +00:00 |
|
rust_bridge
|
fix!: backport the second batch of rc/1.107.0 CI triage fixes from main (#47090)
|
2026-10-17 00:20:23 -07:00 |
|
sandbox
|
refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)
|
2026-10-15 21:08:47 +00:00 |
|
search
|
refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)
|
2026-10-15 21:08:47 +00:00 |
|
secret_managers
|
refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)
|
2026-10-15 21:08:47 +00:00 |
|
skills
|
refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)
|
2026-10-15 21:08:47 +00:00 |
|
systemone
|
feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)
|
2026-11-10 17:08:29 +00:00 |
|
telemetry
|
refactor: clean up fresh tech debt in per-user Copilot auth, Ternary FOCUS export and telemetry (#45769)
|
2026-10-15 04:29:27 +00:00 |
|
tracing
|
fix(proxy): cooldown errors carry 429, Sentry starts at boot without request bodies, tracing failures log at ERROR, exporter counters exported (#46344)
|
2026-10-16 00:53:52 +00:00 |
|
types
|
feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)
|
2026-11-10 17:08:29 +00:00 |
|
vector_store_files
|
refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)
|
2026-10-15 21:08:47 +00:00 |
|
vector_stores
|
feat(count_tokens)!: backport the count_tokens stack to rc/1.107.0 (#46839, #46843, #46583, #47057, #47064, #47163, #46777) (#47209)
|
2026-10-17 18:20:22 -07:00 |
|
videos
|
feat(videos): serve custom_provider_map BaseVideoConfig providers on /v1/videos (#49785)
|
2026-11-05 01:39:40 +00:00 |
|
__init__.py
|
feat(proxy): opt-in free-tier allowance for Google Search grounding spend (#47494)
|
2026-10-27 19:57:38 -07:00 |
|
_internal_context.py
|
fix(anthropic): skip the SDK num_retries retry for an attempt that is sent again
|
2026-11-07 09:28:59 -08:00 |
|
_lazy_imports.py
|
refactor: expose core private helpers under public names (#44871)
|
2026-10-07 00:05:27 +00:00 |
|
_lazy_imports_registry.py
|
feat(typesafe): support Jev 1.14 images, box questions, and long-context headers (#46596)
|
2026-10-14 22:29:48 -07:00 |
|
_logging.py
|
refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)
|
2026-10-15 21:08:47 +00:00 |
|
_redis.py
|
refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)
|
2026-10-15 21:08:47 +00:00 |
|
_redis_credential_provider.py
|
refactor: expose core private helpers under public names (#44871)
|
2026-10-07 00:05:27 +00:00 |
|
_service_logger.py
|
fix(caching): report Redis circuit-breaker metrics through the Prometheus services logger (#46484)
|
2026-10-14 14:29:54 -07:00 |
|
_uuid.py
|
|
|
|
_version.py
|
feat(sdk): build core from an independent packaging manifest (#44340)
|
2026-10-08 18:40:14 -07:00 |
|
anthropic_beta_headers_config.json
|
fix(vertex_ai): forward the inline-tools-2026-09-15 beta to Vertex and Anthropic (#45297)
|
2026-10-08 12:27:52 -07:00 |
|
anthropic_beta_headers_manager.py
|
fix(bedrock): forward the per-turn-control beta to Bedrock Invoke (#43086)
|
2026-11-05 22:42:57 -08:00 |
|
blog_posts.json
|
|
|
|
budget_manager.py
|
refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)
|
2026-10-15 21:08:47 +00:00 |
|
constants.py
|
fix(mcp): backport #47034 to lts/1.108.x
|
2026-11-06 17:08:23 -08:00 |
|
cost.json
|
|
|
|
cost_calculator.py
|
fix(cost): bill transcriptions by the seconds the provider reports
|
2026-11-10 06:21:04 +00:00 |
|
exceptions.py
|
feat(count_tokens)!: backport the count_tokens stack to rc/1.107.0 (#46839, #46843, #46583, #47057, #47064, #47163, #46777) (#47209)
|
2026-10-17 18:20:22 -07:00 |
|
main.py
|
feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)
|
2026-11-10 17:08:29 +00:00 |
|
model_prices_and_context_window_backup.json
|
fix(bedrock): forward the per-turn-control beta to Bedrock Invoke (#43086)
|
2026-11-05 22:42:57 -08:00 |
|
policy_templates_backup.json
|
fix(packaging): keep wheel paths under Windows MAX_PATH for Store Python (#43903)
|
2026-09-30 22:20:36 +00:00 |
|
provider_endpoints_support_backup.json
|
feat(providers): add Inference APIs as OpenAI-compatible provider (#41669)
|
2026-10-15 08:17:36 -07:00 |
|
py.typed
|
|
|
|
router.py
|
fix(videos)!: keep model_id in proxy video ids so per-model keys resolve on status/content (#44614)
|
2026-11-09 15:05:22 +00:00 |
|
scheduler.py
|
fix(scheduler): remove a request's queue entry once it stops waiting (#43061)
|
2026-10-07 17:34:38 -07:00 |
|
setup_wizard.py
|
fix(model_prices): correct Claude Sonnet 5.5 capabilities and provider keys (#43587)
|
2026-09-28 19:12:31 +00:00 |
|
timeout.py
|
|
|
|
tool_loop.py
|
fix(responses bridge): round-trip tool_search_call and tool_search_output items between turns (#46444)
|
2026-10-14 21:40:14 -07:00 |
|
utils.py
|
fix(anthropic): stop SDK retries from resending a rejected block or clearing the global num_retries
|
2026-11-07 10:22:13 -08:00 |
58c13a5290